The growing use of clusters in diverse applications, many of which have real-time constraints, requires Quality-of-Service (QoS) support from the underlying cluster interconnect. In this paper, we present an analytical model for a wormhole-switched router with QoS provisioning. In particular, the model captures message blocking due to wormhole switching and bandwidth sharing due to a rate-based scheduling mechanism. Average message latency for di erent trac classes is computed using the model. We evaluate a 16-port router and hypercubes of di erent dimensions with a mixed workload of real-time and best-e ort trac. Comparison with the simulation results shows that the single router and the network models are quite accurate in providing the performance estimates.